CN114913008A - Decision tree-based bond value analysis method, device, equipment and storage medium - Google Patents
Decision tree-based bond value analysis method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114913008A CN114913008A CN202210369485.6A CN202210369485A CN114913008A CN 114913008 A CN114913008 A CN 114913008A CN 202210369485 A CN202210369485 A CN 202210369485A CN 114913008 A CN114913008 A CN 114913008A
- Authority
- CN
- China
- Prior art keywords
- current
- information
- attribute
- bond
- decision tree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of artificial intelligence, and discloses a decision tree-based bond value analysis method, a decision tree-based bond value analysis device, decision tree-based bond value analysis equipment and a decision tree-based bond value analysis storage medium, wherein the decision tree-based bond value analysis device comprises the following steps: acquiring current bond data, and extracting current attribute information in the current bond data; judging the type information of the current bond data according to the attribute label in the current attribute information through a preset decision tree model; and calling a calculation model corresponding to the type information to perform operation processing on the current attribute information to obtain operation result information corresponding to the current bond data. The invention improves the classification efficiency and the classification accuracy, avoids the condition that the final operation result is inaccurate due to calling an incorrect or inaccurate model caused by a larger error generated by experience because a calculation model is obtained based on the experience of a trader at present, and improves the operation efficiency of the operation result information.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a decision tree-based bond value analysis method, device, equipment and storage medium.
Background
The current bond inventory on the market has reached nearly one hundred thousand, and the value of the bond is generally defined as row right information (i.e., the redemption price of the bond on the right day); however, each bond may adjust the value parameter (for example, bond interest rate) of the bond according to the operation condition of the issuing enterprise, so that, in an objective summary, it can be understood that the real value of each bond may change continuously every day; therefore, current bond trading establishments typically re-evaluate or calculate the true value of each bond based on the experience of the trader.
However, the inventor found that the inefficiency of evaluation or calculation limited to traders and the large error generated by the evaluation or calculation based on experience lead to the problems that the evaluation or calculation of the actual value of the bond is not efficient and the accuracy of the evaluation or calculation result is not high.
Disclosure of Invention
The invention aims to provide a decision tree-based bond value analysis method, a decision tree-based bond value analysis device, decision tree-based bond value analysis equipment and a decision tree-based bond value analysis storage medium, which are used for solving the problems that in the prior art, the evaluation or calculation efficiency limited to traders is low, and the evaluation or calculation efficiency is low due to large errors generated by experience evaluation or calculation, and the evaluation or calculation result is not high in accuracy.
In order to achieve the above object, the present invention provides a decision tree-based bond value analysis method, including:
acquiring current bond data, and extracting current attribute information in the current bond data;
judging the type information of the current bond data according to an attribute label in the current attribute information through a preset decision tree model, wherein the attribute label describes the characteristics of the target bond data in dimension;
and calling a calculation model corresponding to the type information to perform operation processing on the current attribute information to obtain operation result information corresponding to the current bond data, wherein the operation result information represents the real value of the current bond data.
In the foregoing solution, before the obtaining of the current bond data, the method further includes:
acquiring historical bond data, and acquiring target bond data in the historical bond data according to a preset identification rule;
and sequentially extracting historical attribute information of the target bond data, constructing a decision tree model by taking an attribute label in the historical attribute information as a classification condition, and making type information for representing the classification of the decision tree model on the historical attribute information in the decision tree model, wherein the attribute label describes the characteristics of the target bond data in a dimension.
In the above scheme, the acquiring historical bond data and acquiring target bond data from the historical bond data according to a preset identification rule includes:
acquiring historical bond data from a preset historical library according to preset cycle information, wherein the cycle information defines the time for acquiring the historical bond data from the historical library;
extracting keywords in the identification rule, identifying historical bond data with the keywords from the historical bond data, and setting the historical bond data with the keywords as the target bond data.
In the above scheme, the sequentially extracting the historical attribute information of the target bond data, and constructing a decision tree model with the attribute labels in the historical attribute information as classification conditions includes:
extracting attribute tags in the historical attribute information;
arranging and combining the attribute tags to obtain an attribute set, wherein at least the attribute tags are arranged in the attribute set;
and taking the attribute set as a preset classification target of an initial tree model, and constructing a classification condition for classifying the attribute set in the initial tree model to convert the initial tree model into a decision tree model.
In the above scheme, the making type information used for characterizing the classification of the decision tree model on the historical attribute information in the decision tree model includes:
acquiring a terminal node of the decision tree model, wherein the terminal node is a node which is in the decision tree model and only has the attribute set;
defining type information in the end node for characterizing the attribute set in the end node, wherein the type information characterizes classification of the historical attribute information by the decision tree model.
In the foregoing solution, before the invoking of the computation model corresponding to the type information performs operation processing on the current attribute information, the method further includes:
constructing a calculation model corresponding to the type information, wherein the calculation model is used for calculating current attribute information corresponding to the type information;
the constructing of the calculation model corresponding to the type information includes:
constructing a calculation model corresponding to the type information in the decision tree, wherein an operation strategy for operating the current attribute information is recorded in the calculation model;
and constructing a trigger connection between a node unit of the decision tree model and the calculation model, wherein the node unit is a computer module used for recording type information in the decision tree model.
In the foregoing solution, the invoking a calculation model corresponding to the type information to perform operation processing on the current attribute information to obtain operation result information corresponding to the current bond data includes:
acquiring a calculation model corresponding to the type information from a preset model library, setting an attribute label in the current attribute information as a current attribute label, and setting a result label in the current attribute information as a current result label;
inputting the current attribute label and the value corresponding to the current attribute label in the current attribute information and/or the current result label and the value corresponding to the current attribute label in the current attribute information into the calculation model, so that the calculation model is converted into a model to be calculated;
calling a preset computing thread to run the model to be computed to obtain the computation result information corresponding to the current bond data, wherein the computing thread is a scheduling unit used for providing computation resources for the model to be computed;
and uploading the operation result information to a block chain.
In order to achieve the above object, the present invention further provides a decision tree-based bond value analysis apparatus, including:
the attribute acquisition module is used for acquiring current bond data and extracting current attribute information in the current bond data;
the type judging module is used for judging the type information of the current bond data according to an attribute label in the current attribute information through a preset decision tree model, wherein the attribute label describes the characteristics of the target bond data in dimension;
and the data operation module is used for calling a calculation model corresponding to the type information to perform operation processing on the current attribute information to obtain operation result information corresponding to the current bond data, wherein the operation result information represents the real value of the current bond data.
In order to achieve the above object, the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and operable on the processor, wherein the processor of the computer device implements the steps of the bond value analysis method when executing the computer program.
In order to achieve the above object, the present invention further provides a computer-readable storage medium, having a computer program stored thereon, where the computer program stored in the computer-readable storage medium, when executed by a processor, implements the steps of the bond value analysis method.
According to the decision tree-based bond value analysis method, device, equipment and storage medium, the type information of the current bond data is judged through the decision tree model according to the attribute labels in the current attribute information, so that the technical effect of automatically classifying the current bond data is achieved, the classification efficiency and the classification accuracy are further improved, and therefore the matching accuracy between the subsequently acquired calculation model and the current bond data is guaranteed.
The calculation model corresponding to the type information is called to carry out operation processing on the current attribute information, so that the technical effect of accurately obtaining the calculation model corresponding to the current bond data is achieved, and the condition that the final operation result is inaccurate due to calling of an error or inaccurate model caused by a large error generated by experience caused by obtaining the calculation model based on experience of a trader is avoided; the current attribute information is operated through the calculation model to obtain operation result information corresponding to the current bond data, so that the operation result information of the current bond data is automatically calculated, the operation efficiency of the operation result information is improved, and the problem of low calculation efficiency caused by the fact that an evaluation model or a calculation model is manually called by a trader to calculate the bond data at present is avoided.
Drawings
FIG. 1 is a flow chart of a bond value analysis method according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of an environmental application of a bond value analysis method according to a second embodiment of the bond value analysis method of the present invention;
FIG. 3 is a flow chart of a method for analyzing bond value according to a second embodiment of the method for analyzing bond value of the present invention;
fig. 4 is a schematic diagram of program modules of a third embodiment of the bond value analysis apparatus according to the present invention;
fig. 5 is a schematic diagram of a hardware structure of a computer device according to a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The decision tree-based bond value analysis method, device, equipment and storage medium provided by the invention are suitable for the technical field of artificial intelligence intelligent decision, and are used for providing a bond value analysis method based on an attribute acquisition module, a type judgment module and a data operation module. The method comprises the steps of extracting current attribute information in current bond data by acquiring the current bond data; judging the type information of the current bond data according to the attribute label in the current attribute information through a preset decision tree model; and calling a calculation model corresponding to the type information to perform operation processing on the current attribute information to obtain operation result information corresponding to the current bond data.
The first embodiment is as follows:
referring to fig. 1, a method for analyzing bond value based on decision tree in this embodiment includes:
s103: acquiring current bond data, and extracting current attribute information in the current bond data;
s104: judging the type information of the current bond data according to an attribute label in the current attribute information through a preset decision tree model, wherein the attribute label describes the characteristics of the target bond data in dimension;
s106: and calling a calculation model corresponding to the type information to perform operation processing on the current attribute information to obtain operation result information corresponding to the current bond data, wherein the operation result information represents the real value of the current bond data.
In an exemplary embodiment, current bond data sent by a terminal or a bond number sent by a management end is received, and the current bond data is obtained from a preset bond database according to the bond number, wherein the current attribute information is used for describing the current bond data in a dimension, and a current attribute tag used for describing the current bond data in a certain dimension is included in the current attribute information.
And judging the type information of the current bond data according to the attribute label in the current attribute information through the decision tree model so as to realize the technical effect of automatically classifying the current bond data and further improve the classification efficiency and the classification accuracy, thereby ensuring the matching accuracy between the subsequently acquired calculation model and the current bond data.
The calculation model corresponding to the type information is called to carry out operation processing on the current attribute information, so that the technical effect of accurately obtaining the calculation model corresponding to the current bond data is achieved, and the condition that the final operation result is inaccurate due to calling of an error or inaccurate model caused by a large error generated by experience caused by obtaining the calculation model based on experience of a trader is avoided; the current attribute information is operated through the calculation model to obtain operation result information corresponding to the current bond data, so that the operation result information of the current bond data is automatically calculated, the operation efficiency of the operation result information is improved, and the problem of low calculation efficiency caused by the fact that an evaluation model or a calculation model is manually called by a trader to calculate the bond data at present is avoided.
Example two:
the embodiment is a specific application scenario of the first embodiment, and the method provided by the present invention can be more clearly and specifically explained through the embodiment.
The method provided by the present embodiment will be specifically described below by taking an example in which, in a server running a bond value analysis method, type information of current bond data is determined by a decision tree model, and a calculation model corresponding to the type information is called to perform calculation processing on current attribute information to obtain calculation result information. It should be noted that the present embodiment is only exemplary, and does not limit the protection scope of the embodiments of the present invention.
Fig. 2 schematically shows an environmental application diagram of the bond value analysis method according to the second embodiment of the present application.
In an exemplary embodiment, the server 2 in which the bond value analysis method is located is respectively connected with the development end 3, the terminal 4 and the management end 5 through a network; the server 2 may provide services over a network that may include various network devices such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices, and/or the like. The network may include physical links, such as coaxial cable links, twisted pair cable links, fiber optic links, combinations thereof, and/or the like. The network may include wireless links, such as cellular links, satellite links, Wi-Fi links, and/or the like; the development end 3, the terminal 4 and the management end 5 can be respectively computer equipment such as a smart phone, a tablet computer, a notebook computer, a desktop computer and the like.
Fig. 3 is a flowchart of a method for analyzing bond value according to an embodiment of the present invention, and the method includes steps S201 to S206.
S201: historical bond data are obtained, and target bond data are obtained from the historical bond data according to preset identification rules.
In this step, historical bond data corresponding to a preset number, for example 10000 shares, are acquired from a preset historical library to ensure the comprehensiveness of the types of the historical bond data, and target bond data required by a development end is acquired from the historical bond data through the identification rule, so that the technical effect of acquiring designated data according to the decision tree construction requirement of the development end is achieved, and the pertinence of data acquisition is ensured.
In a preferred embodiment, the obtaining historical bond data and the obtaining target bond data in the historical bond data according to preset identification rules includes:
s11: acquiring historical bond data from a preset historical library according to preset cycle information, wherein the cycle information defines the time for acquiring the historical bond data from the historical library;
s12: extracting keywords in the identification rule, identifying historical bond data with the keywords from the historical bond data, and setting the historical bond data with the keywords as the target bond data.
Specifically, the identification rule comprises a keyword and a screening strategy, wherein the keyword can be set according to needs
The screening policy is a setting mode of the keywords when the historical bonds are screened, for example: and/or.
Illustratively, setting the keywords in the identification rule as "redemption" and "resale", setting the screening policy in the identification rule as "or", obtaining redeemable and/or resolvable bonds from the historical bond data and setting the redeemable and/or resolvable bonds as the target bond data.
S202: and sequentially extracting historical attribute information of the target bond data, constructing a decision tree model by taking an attribute label in the historical attribute information as a classification condition, and making type information for representing the classification of the decision tree model on the historical attribute information in the decision tree model, wherein the attribute label describes the characteristics of the target bond data in a dimension.
In this step, the attribute tag of the historical attribute information includes: redemption right information, resale right information, interest rate adjustment information; the result tag of the historical attribute information includes: the row right information.
In a preferred embodiment, the sequentially extracting the historical attribute information of the target bond data, and constructing a decision tree model with attribute tags in the historical attribute information as classification conditions includes:
s21: extracting attribute tags in the historical attribute information;
s22: arranging and combining the attribute tags to obtain an attribute set, wherein at least the attribute tags are arranged in the attribute set;
s23: and taking the attribute set as a preset classification target of an initial tree model, and constructing a classification condition for classifying the attribute set in the initial tree model to convert the initial tree model into a decision tree model.
Further, the step of constructing a classification condition for classifying the attribute set in the initial tree model by using the attribute set as a classification target of a preset initial tree model, so that the initial tree model is converted into a decision tree model includes:
s231: defining classification times n, wherein n is a positive integer greater than or equal to 1;
s232: when the classification times n is 1, setting all the attribute sets as nth categories;
s233: executing an nth entropy calculation process to obtain attribute labels in all attribute sets under the nth category and perform de-duplication to obtain an nth feature set corresponding to the nth category, and calculating an nth entropy of any attribute label relative to all attribute sets according to the ratio of the attribute set with any attribute label in the nth feature set in all attribute sets, wherein the nth entropy represents the distinguishing capability of the attribute sets by taking the attribute label corresponding to the nth entropy as a classification condition, and the distinguishing capability is in negative correlation with the nth entropy.
In this step, an nth entropy formula is used to calculate an nth entropy value for each attribute tag with respect to all the attribute sets, where the nth entropy formula is:
wherein p is i The ratio of the attribute set with the ith attribute label in the nth feature set to all the attribute sets is defined; e refers to the nth entropy value corresponding to the attribute tag.
S234: executing an nth classification process for obtaining nth entropy values of all attribute tags in the feature set, identifying the lowest value of the nth entropy values of all attribute tags, taking the attribute tag corresponding to the lowest value as an nth classification condition of the initial tree model, and classifying all attribute sets under the nth category through the initial tree model according to the nth classification condition to obtain two subcategories under the nth category;
s235: executing an nth judgment process for judging whether the sub-category under the nth category has and only has an attribute set;
s236: if there are both sub-categories and only attribute sets, then the initial tree model is transformed into a decision tree model.
S237: if only an attribute set exists and only exists under the subcategories in the two subcategories, ending the entropy calculation process and the classification process of the subcategories which have and only exist the attribute set, setting the subcategories which have two or more attribute sets as an n +1 th category, sequentially executing the (n + 1) th entropy calculation process and the (n + 1) th classification process on all the attribute sets under the n +1 th category to obtain two subcategories under the n +1 th category, and then executing the (n + 1) th judgment process on the two subcategories under the n +1 th category;
s238: if two or more attribute sets exist under the two sub-categories, setting the sub-categories with the two or more attribute sets as an n +1 th category, sequentially executing an (n + 1) th entropy calculation process and an (n + 1) th classification process on all the attribute sets under the n +1 th category to obtain two sub-categories under the n +1 th category, and then executing an (n + 1) th judgment process on the two sub-categories under the n +1 th category;
specifically, the ID3 algorithm (Iterative Dichotomiser 3 iteration binary tree 3 generation) is used as the initial tree model, which is built on the basis of the oham razor, i.e.: the smaller the decision tree is, the better the decision tree is than the larger decision tree, and the technical effect of the decision tree model capable of rapidly classifying the historical attribute information is obtained.
Therefore, the attribute set of the attribute tags is used as the classification condition of the decision tree model, the identification of the permutation and combination of various attribute tags in the historical attribute information of the historical bond data is realized, and the technical effect of classifying the historical bond data in a targeted manner is further realized.
Illustratively, a first set of attributes having the redemption right information, the reauthorization information and the interest rate adjustment information at the same time;
setting a set of attributes having both the redemption right information and the redemption right information but not the interest rate adjustment information as a second set;
setting a set of attributes having both the redemption right information and the interest rate adjustment information but no redemption right information as a third set;
setting a set of attributes having both of the redemption right information and the interest rate adjustment information but not the redemption right information as a fourth set;
setting a fifth set of attributes having only the redemption right information but not the redemption right information and the interest rate adjustment information;
the set of attributes having only the redemption right information but not the redemption right information and the interest rate adjustment information is set as a sixth set.
Therefore, the classification conditions of the decision tree model obtained in step S23 are as follows:
the first classification condition is whether interest rate adjustment information is available, and the first set, the third set and the fourth set are classified into subclasses according to the first classification condition, and the second set, the fifth set and the sixth set are classified into another subclass. Wherein the second sub-category is set as the first sub-category and the second sub-category is set as the second sub-category;
a second classification condition for the first sub-category is whether or not there is both redemption right information and redemption right information, the first set is divided into sub-categories according to the second classification condition, the third set and the fourth set are divided into another sub-category; wherein the second sub-category is set as the first sub-category and the second sub-category is set as the second sub-category;
and a second classification condition for the second sub-category is whether there is both redemption right information and redemption right information, the second set is classified as a sub-category according to the second classification condition, the fifth set and the sixth set are classified as another sub-category, wherein the third sub-category is set as a third sub-category, and the second sub-category is set as a fourth sub-category;
classifying the second sub-category if there is redemption right information to classify the third set as one sub-category and the fourth set as another sub-category;
and classifying the fourth sub-category if there is redemption right information to classify the fifth set as one sub-category and the sixth set as another sub-category.
In a preferred embodiment, the making of type information in the decision tree model for characterizing the classification category of the decision tree model on the historical attribute information includes:
s24: acquiring a terminal node of the decision tree model, wherein the terminal node is a node which is in the decision tree model and only has the attribute set;
s25: defining type information in the end node for characterizing the attribute set in the end node, wherein the type information characterizes classification of the historical attribute information by the decision tree model.
Illustratively, a child node corresponding to the classification condition of the first set in the decision tree is obtained, and the type information with the first type of content is defined in the child node;
acquiring child nodes corresponding to the classification conditions of the second set in the decision tree, and defining the type information with the content of the second type in the child nodes;
acquiring child nodes corresponding to the classification conditions of the third set in the decision tree, and defining the type information with the content of the third type in the child nodes;
acquiring child nodes corresponding to the classification conditions of the fourth set in the decision tree, and defining the type information with the fourth type in the child nodes;
acquiring child nodes corresponding to the classification conditions of the fifth set in the decision tree, and defining type information with a fifth type in the child nodes;
and acquiring child nodes corresponding to the classification conditions of the sixth set in the decision tree, wherein the type information with the sixth type content is defined in the child nodes.
S203: and acquiring current bond data, and extracting current attribute information in the current bond data.
In this step, the current bond data sent by the terminal connected to the server 2 in advance or the bond number sent by the management terminal connected to the server 2 in advance is received, and the current bond data is acquired from a preset bond database according to the bond number. The current attribute information is used for describing the current bond data in a dimension, and a current attribute tag used for describing the current bond data in a certain dimension is arranged in the current attribute information.
S204: and judging the type information of the current bond data according to an attribute label in the current attribute information through a preset decision tree model, wherein the attribute label describes the characteristics of the target bond data in dimension.
In order to realize automatic classification of the current bond data and improve the classification efficiency and the classification accuracy of the current bond data, the type information of the current bond data is judged through the decision tree model according to the attribute labels in the current attribute information, so that the technical effect of automatic classification of the current bond data is realized, and the classification efficiency and the classification accuracy are improved.
S205: and constructing a calculation model corresponding to the type information, wherein the calculation model is used for calculating the current attribute information corresponding to the type information.
In order to avoid calculating the current bond data in a manual mode after the current bond data are obtained, the step is used for calculating the current attribute information corresponding to the type information by constructing a calculation model corresponding to the type information, so that the corresponding calculation model is directly called according to the type information, and the current attribute information is calculated, so that the risk that the calculation efficiency of the current attribute information is low and the error rate is high due to the fact that the current manual mode is adopted is avoided.
In a preferred embodiment, the constructing the calculation model corresponding to the type information includes:
s51: constructing a calculation model corresponding to the type information in the decision tree, wherein an operation strategy for operating the current attribute information is recorded in the calculation model;
s52: and constructing a trigger connection between a node unit of the decision tree model and the calculation model, wherein the node unit is a computer module used for recording type information in the decision tree model.
In the embodiment, the current attribute information is calculated according to the type information in a targeted manner by constructing the calculation model, so that the problem of low calculation efficiency caused by the fact that the current bond data needs to be calculated by manually calling a corresponding calculation formula is solved.
By establishing triggering connection between the node unit and the calculation model, the decision tree model can directly call the calculation model corresponding to the type information after classifying the current bond data and obtaining the type information corresponding to the current bond data, and calculate the current attribute information of the current bond data, thereby realizing seamless connection of type identification and data calculation, and avoiding the occurrence of calculation errors caused by easily calling the model by mistake due to the fact that the preset calculation model needs to be manually called currently.
Illustratively, when the content of the type information is of a first type, the operation policy of the calculation model corresponding to the type information is: taking a result label in the current attribute information as operation result information;
when the content of the type information is of a second type, the operation strategy of the calculation model corresponding to the type information is as follows: taking a result label in the current attribute information as operation result information;
when the content of the type information is a third type, the operation strategy of the calculation model corresponding to the type information is as follows: judging whether preset bond keywords (such as values corresponding to capital supplement bonds) exist in the current bond data;
if yes, taking a result label of the current bond data as operation result information; if not, adjusting the result label of the current bond data according to the interest rate adjustment information to obtain row right adjustment information, and taking the row right adjustment information as the operation result information;
when the content of the type information is a fourth type, the operation strategy of the calculation model corresponding to the type information is as follows: identifying the adjustment content of the interest rate adjustment weight information; if the adjustment content is an adjustable interest rate and an adjustable interest rate, and the interest rate adjustment information does not have an adjustable boundary when the interest rate is adjusted downwards, taking the right information as the operation result information; if the adjustment content is only the interest rate which can be adjusted upwards, calling a preset pricing model to calculate the resale right information to obtain pricing prediction information, and taking the pricing prediction information as the operation result information;
when the content of the type information is a fifth type, the operation strategy of the calculation model corresponding to the type information is as follows: and calling a preset pricing model to calculate the redemption right information to obtain operation result information. In this embodiment, a Hull White model may be used as the calculation model;
when the content of the type information is a sixth type, the operation policy of the calculation model corresponding to the type information is as follows: and calling a preset pricing model to calculate the selling right information to obtain the operation result information. In this embodiment, a Hull White model may be used as the computational model.
In this embodiment, the operation result information represents the actual value of the current bond data.
The Hull White model is a Hull-White model, which is one of interest rate models in financial mathematics. In this model, in order to convert the future interest rate variation into a mathematically simple Lattice model, the interest rate is evaluated by a choice model evaluation model using the interest rate as a large choice (a choice that can be executed during a plurality of periods set in a choice existence period) of a hundred mu.
S206: and calling a calculation model corresponding to the type information to perform operation processing on the current attribute information to obtain operation result information corresponding to the current bond data, wherein the operation result information represents the real value of the current bond data.
In order to automatically and accurately calculate the calculation result information of the current bond data, the calculation model corresponding to the type information is called to perform calculation processing on the current attribute information, so that the technical effect of accurately acquiring the calculation model corresponding to the current bond data is realized, and the condition that the final calculation result is inaccurate due to calling an incorrect or inaccurate model caused by a large error generated by experience because the calculation model is acquired based on experience of a trader at present is avoided; the current attribute information is operated through the calculation model to obtain operation result information corresponding to the current bond data, so that the operation result information of the current bond data is automatically calculated, the operation efficiency of the operation result information is improved, and the problem of low calculation efficiency caused by the fact that an evaluation model or a calculation model is manually called by a trader to calculate the bond data at present is avoided.
In a preferred embodiment, the invoking a calculation model corresponding to the type information to perform operation processing on the current attribute information to obtain operation result information corresponding to the current bond data includes:
s61: acquiring a calculation model corresponding to the type information from a preset model library, setting an attribute label in the current attribute information as a current attribute label, and setting a result label in the current attribute information as a current result label;
s62: inputting the current attribute label and the value corresponding to the current attribute label in the current attribute information and/or the current result label and the value corresponding to the current attribute label in the current attribute information into the calculation model, so that the calculation model is converted into a model to be calculated;
s63: and calling a preset computing thread to run the model to be computed to obtain the computation result information corresponding to the current bond data, wherein the computing thread is a scheduling unit used for providing computation resources for the model to be computed.
Specifically, a thread pool is constructed in a server running a decision tree-based bond management method, wherein the thread pool is provided with a computing thread with an idle state, and the computing thread is used for providing computing resources for the running of the computing model;
and acquiring a calculation model corresponding to the type information from a model library in which the calculation model is stored, wherein the type information and the calculation model are stored in the model library in a key-value pair manner, so as to quickly acquire the calculation model according to the type information.
And comparing the current attribute tag and the value thereof corresponding to the current attribute information, and/or the current result tag and the value thereof corresponding to the current attribute information, for example: and inputting the numerical value of the redemption right information and the numerical value m% of the interest rate adjustment information into the calculation model, and converting the calculation model into the model to be operated.
Identifying whether a computing thread with an idle state exists in the thread pool;
if so, converting the state of the computing thread into busy, and calling the computing thread to run the model to be operated to obtain the operation result information corresponding to the current bond data; when the operation result information is obtained, releasing the calculation thread and enabling the state of the calculation thread to be idle;
if not, the serial number of the model to be operated is recorded into a preset queue; and when a computing thread with an idle state appears in the thread pool, acquiring a serial number from the queue, acquiring a model to be operated corresponding to the serial number, and calling the computing thread with the idle state to operate the model to be operated to obtain the operation result information.
Preferably, after the preset computing thread is called to run the model to be computed to obtain the computation result information corresponding to the current bond data, the method further includes:
and uploading the operation result information to a block chain.
The corresponding digest information is obtained based on the operation result information, and specifically, the digest information is obtained by hashing the operation result information, for example, by using the sha256s algorithm. Uploading summary information to the blockchain can ensure the safety and the fair transparency of the user. The user equipment can download the summary information from the blockchain so as to verify whether the operation result information is tampered. The blockchain referred to in this example is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, and the like. A block chain (Blockchain), which is essentially a decentralized database, is a string of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, which is used for verifying the validity (anti-counterfeiting) of the information and generating a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Example three:
referring to fig. 4, the decision tree-based bond value analysis apparatus 1 of the present embodiment includes:
the attribute acquisition module 13 is configured to acquire current bond data and extract current attribute information in the current bond data;
a type determining module 14, configured to determine type information of the current bond data according to an attribute tag in the current attribute information through a preset decision tree model, where the attribute tag describes a feature of the target bond data in a dimension;
and the data operation module 16 is configured to invoke a calculation model corresponding to the type information to perform operation processing on the current attribute information, so as to obtain operation result information corresponding to the current bond data, where the operation result information represents a real value of the current bond data.
Optionally, the bond value analysis apparatus 1 further includes:
and the data acquisition module 11 is configured to acquire historical bond data and acquire target bond data from the historical bond data according to preset identification rules.
Optionally, the data obtaining module 11 includes:
a data obtaining unit 111 configured to obtain historical bond data from a preset historical repository according to preset cycle information, where the cycle information defines a time for obtaining the historical bond data from the historical repository;
a data identification unit 112, configured to extract a keyword in the identification rule, identify historical bond data with the keyword from the historical bond data, and set the historical bond data with the keyword as the target bond data.
Optionally, the bond value analysis apparatus 1 further includes:
the model building module 12 is configured to sequentially extract historical attribute information of the target bond data, build a decision tree model by using an attribute tag in the historical attribute information as a classification condition, and make type information used for representing a classification of the historical attribute information by the decision tree model in the decision tree model, where the attribute tag describes characteristics of the target bond data in a dimension.
Optionally, the model building module 12 includes:
a tag extracting unit 121, configured to extract an attribute tag in the history attribute information;
the attribute arrangement unit 122 is configured to perform arrangement and combination on the attribute tags to obtain an attribute set, where at least an attribute tag is included in the attribute set;
a model constructing unit 123, configured to use the attribute set as a classification target of a preset initial tree model, and construct a classification condition for classifying the attribute set in the initial tree model, so that the initial tree model is converted into a decision tree model.
A node obtaining unit 124, configured to obtain an end node of the decision tree model, where the end node is a node in the decision tree model that has only the attribute set;
a type defining unit 125, configured to define, in the end node, type information for characterizing the attribute set in the end node, where the type information characterizes a classification category of the historical attribute information by the decision tree model.
Optionally, the bond value analysis apparatus 1 further includes:
and a calculation construction module 15, configured to construct a calculation model corresponding to the type information, where the calculation model is used to calculate current attribute information corresponding to the type information.
Optionally, the calculation building module 15 includes:
a calculation construction unit 151, configured to construct a calculation model corresponding to the type information in the decision tree, where an operation strategy for performing an operation on current attribute information is recorded in the calculation model;
a trigger setting unit 152, configured to construct a trigger connection between a node unit of the decision tree model and the computation model, where the node unit is a computer module in the decision tree model for recording type information.
Optionally, the data operation module 16 includes:
a tag identification unit 161, configured to obtain a calculation model corresponding to the type information from a preset model library, set an attribute tag in the current attribute information as a current attribute tag, and set a result tag in the current attribute information as a current result tag;
a model conversion unit 162, configured to enter the current attribute tag and the corresponding value thereof in the current attribute information, and/or the current result tag and the corresponding value thereof in the current attribute information into the computation model, so that the computation model is converted into a model to be computed;
and a model running unit 163, configured to invoke a preset computing thread to run the model to be operated to obtain the operation result information corresponding to the current bond data, where the computing thread is a scheduling unit configured to provide an operation resource for the model to be operated.
The technical scheme is applied to the field of intelligent decision of artificial intelligence, and a decision tree model is used as a classification model for judging the type information of the current bond data according to the attribute label in the current attribute information; and calling a calculation model corresponding to the type information to perform operation processing on the current attribute information to obtain operation result information corresponding to the current bond data.
Example four:
in order to achieve the above object, the present invention further provides a computer device 6, components of the bond value analysis apparatus in the third embodiment may be dispersed in different computer devices, and the computer device 6 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack-mounted server, a blade server, a tower server, or a rack-mounted server (including an independent server or a server cluster formed by application servers) for executing programs, and the like. The computer device of the embodiment at least includes but is not limited to: a memory 61, a processor 62, which may be communicatively coupled to each other via a system bus, as shown in fig. 5. It should be noted that fig. 5 only shows a computer device with components, but it should be understood that not all of the shown components are required to be implemented, and more or fewer components may be implemented instead.
In the present embodiment, the memory 61 (i.e., a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory 61 may be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. In other embodiments, the memory 61 may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the computer device. Of course, the memory 61 may also include both internal and external storage devices of the computer device. In this embodiment, the memory 61 is generally used for storing an operating system and various application software installed in the computer device, for example, a program code of the bond value analysis apparatus according to the third embodiment. Further, the memory 61 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 62 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 62 is typically used to control the overall operation of the computer device. In this embodiment, the processor 62 is configured to operate the program codes stored in the memory 61 or process data, for example, operate the bond value analysis device, so as to implement the bond value analysis methods of the first and second embodiments.
Example five:
to achieve the above objects, the present invention also provides a computer readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App, etc., having a computer program stored thereon that when executed by a processor 62 implements corresponding functions. The computer-readable storage medium of the present embodiment is used for storing a computer program for implementing the bond value analysis method, and when executed by the processor 62, implements the bond value analysis method of the first and second embodiments.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A decision tree-based bond value analysis method is characterized by comprising the following steps:
acquiring current bond data, and extracting current attribute information in the current bond data;
judging the type information of the current bond data according to an attribute label in the current attribute information through a preset decision tree model, wherein the attribute label describes the characteristics of the target bond data in dimension;
and calling a calculation model corresponding to the type information to perform operation processing on the current attribute information to obtain operation result information corresponding to the current bond data, wherein the operation result information represents the real value of the current bond data.
2. The bond value analysis method of claim 1, wherein prior to the obtaining current bond data, the method further comprises:
acquiring historical bond data, and acquiring target bond data in the historical bond data according to a preset identification rule;
and sequentially extracting historical attribute information of the target bond data, constructing a decision tree model by taking an attribute label in the historical attribute information as a classification condition, and making type information for representing the classification of the decision tree model on the historical attribute information in the decision tree model, wherein the attribute label describes the characteristics of the target bond data in a dimension.
3. The bond value analysis method according to claim 2, wherein the obtaining of the historical bond data and the obtaining of the target bond data in the historical bond data according to the preset identification rule comprise:
acquiring historical bond data from a preset historical library according to preset cycle information, wherein the cycle information defines the time for acquiring the historical bond data from the historical library;
extracting keywords in the identification rule, identifying historical bond data with the keywords from the historical bond data, and setting the historical bond data with the keywords as the target bond data.
4. The bond value analysis method according to claim 2, wherein the sequentially extracting historical attribute information of the target bond data and constructing a decision tree model with attribute labels in the historical attribute information as classification conditions comprises:
extracting attribute tags in the historical attribute information;
arranging and combining the attribute tags to obtain an attribute set, wherein at least the attribute tags are arranged in the attribute set;
and taking the attribute set as a preset classification target of an initial tree model, and constructing a classification condition for classifying the attribute set in the initial tree model to convert the initial tree model into a decision tree model.
5. The bond value analysis method according to claim 2, wherein the formulating type information in the decision tree model for characterizing the classification of the decision tree model on the historical attribute information comprises:
acquiring a terminal node of the decision tree model, wherein the terminal node is a node which is in the decision tree model and only has the attribute set;
defining type information in the end node for characterizing the attribute set in the end node, wherein the type information characterizes classification of the historical attribute information by the decision tree model.
6. The bond value analysis method according to claim 1, wherein before the calling the calculation model corresponding to the type information to perform the operation processing on the current attribute information, the method further comprises:
constructing a calculation model corresponding to the type information, wherein the calculation model is used for calculating current attribute information corresponding to the type information;
the constructing of the calculation model corresponding to the type information includes:
constructing a calculation model corresponding to the type information in the decision tree, wherein an operation strategy for operating the current attribute information is recorded in the calculation model;
and constructing a trigger connection between a node unit of the decision tree model and the calculation model, wherein the node unit is a computer module used for recording type information in the decision tree model.
7. The bond value analysis method according to claim 1, wherein the invoking of the calculation model corresponding to the type information to perform calculation processing on the current attribute information to obtain calculation result information corresponding to the current bond data comprises:
acquiring a calculation model corresponding to the type information from a preset model library, setting an attribute label in the current attribute information as a current attribute label, and setting a result label in the current attribute information as a current result label;
inputting the current attribute label and the value corresponding to the current attribute label in the current attribute information and/or the current result label and the value corresponding to the current attribute label in the current attribute information into the calculation model, so that the calculation model is converted into a model to be calculated;
calling a preset computing thread to run the model to be computed to obtain the computation result information corresponding to the current bond data, wherein the computing thread is a scheduling unit used for providing computation resources for the model to be computed;
and uploading the operation result information to a block chain.
8. A decision tree-based bond value analysis device is characterized by comprising:
the attribute acquisition module is used for acquiring current bond data and extracting current attribute information in the current bond data;
the type judging module is used for judging the type information of the current bond data according to an attribute label in the current attribute information through a preset decision tree model, wherein the attribute label describes the characteristics of the target bond data in dimension;
and the data operation module is used for calling a calculation model corresponding to the type information to perform operation processing on the current attribute information to obtain operation result information corresponding to the current bond data, wherein the operation result information represents the real value of the current bond data.
9. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the steps of the bond value analysis method of any one of claims 1 to 7 are implemented by the processor of the computer device when the computer program is executed.
10. A computer-readable storage medium on which a computer program is stored, the computer program stored in the computer-readable storage medium, when being executed by a processor, implementing the steps of the bond value analysis method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210369485.6A CN114913008A (en) | 2022-04-08 | 2022-04-08 | Decision tree-based bond value analysis method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210369485.6A CN114913008A (en) | 2022-04-08 | 2022-04-08 | Decision tree-based bond value analysis method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114913008A true CN114913008A (en) | 2022-08-16 |
Family
ID=82763801
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210369485.6A Pending CN114913008A (en) | 2022-04-08 | 2022-04-08 | Decision tree-based bond value analysis method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114913008A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116702059A (en) * | 2023-06-05 | 2023-09-05 | 苏州市联佳精密机械有限公司 | Intelligent production workshop management system based on Internet of things |
-
2022
- 2022-04-08 CN CN202210369485.6A patent/CN114913008A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116702059A (en) * | 2023-06-05 | 2023-09-05 | 苏州市联佳精密机械有限公司 | Intelligent production workshop management system based on Internet of things |
| CN116702059B (en) * | 2023-06-05 | 2023-12-19 | 苏州市联佳精密机械有限公司 | Intelligent production workshop management system based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110609759B (en) | Fault root cause analysis method and device | |
| WO2020140386A1 (en) | Textcnn-based knowledge extraction method and apparatus, and computer device and storage medium | |
| CN108764273A (en) | A kind of method, apparatus of data processing, terminal device and storage medium | |
| CN113688923B (en) | Order abnormity intelligent detection method and device, electronic equipment and storage medium | |
| CN111444956B (en) | Low-load information prediction method, device, computer system and readable storage medium | |
| CN112579462B (en) | Test case acquisition method, system, equipment and computer readable storage medium | |
| CN111371858A (en) | Group control equipment identification method, device, medium and electronic equipment | |
| CN112231416A (en) | Knowledge graph ontology updating method and device, computer equipment and storage medium | |
| CN113568740A (en) | Model aggregation method, system, device and medium based on federal learning | |
| CN113824575B (en) | Method and device for identifying fault node, computing equipment and computer storage medium | |
| CN114913008A (en) | Decision tree-based bond value analysis method, device, equipment and storage medium | |
| CN111625567A (en) | Data model matching method, device, computer system and readable storage medium | |
| CN113283222B (en) | Automatic report generation method and device, computer equipment and storage medium | |
| CN111831817B (en) | Questionnaire generation analysis method, device, computer device and readable storage medium | |
| CN111950623B (en) | Data stability monitoring method, device, computer equipment and medium | |
| CN112069822B (en) | Word vector representation acquisition method, device, equipment and readable medium | |
| CN113420887A (en) | Prediction model construction method and device, computer equipment and readable storage medium | |
| CN113591881A (en) | Intention recognition method and device based on model fusion, electronic equipment and medium | |
| CN116629423A (en) | User behavior prediction method, device, equipment and storage medium | |
| CN115146653B (en) | Dialogue scenario construction method, device, equipment and storage medium | |
| CN114266255B (en) | Corpus classification method, apparatus, device and storage medium based on clustering model | |
| CN113673229B (en) | Electric power marketing data interaction method, system and storage medium | |
| CN115099875A (en) | Data classification method based on decision tree model and related equipment | |
| CN113298645B (en) | Resource quota adjustment method and device and electronic equipment | |
| CN111046892A (en) | Abnormity identification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |